Dev Radar
Support
LiveUpdated 2026-11-05 10:12 UTC

Got Ripple-65B Preview by @RicursiveAI running on one DGX Spark w/Hermes agent. Congrats…

Got Ripple-65B Preview by @RicursiveAI running on one DGX Spark w/Hermes agent. Congrats on the release, @Azaliamirh…

This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.

Got Ripple-65B Preview by @RicursiveAI running on one DGX Spark w/Hermes agent. Congrats on the release, @Azaliamirh and @annadgoldie. NVFP4 weights, Ricursive’s BF16 draft for DFlash2 (@zhijianliu), and 128K context configured. Hooked it into DeepSeek Harness with streaming and tool calls working. Across three measured runs per prompt: Code: 20.5 tok/s Edits: 26.6 tok/s Prose: 7.6 tok/s Those are end to end rates. The gap between code and prose surprised me. Tried a vLLM backport and shorter draft blocks too. Both helped some prompts and hurt others, so I’m still on the original SGL

Posted by Joey (4.9k followers) 2 h ago · 8 likes · 487 views · view the original post on X. Kept by the Dev Radar as AI dev tools.

More dev work like this

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.7k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 10:12 UTC. Full method.